© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 2602
    Prev
    Next
    INDEX
    Explanations

    mentions of civilian-related terms, especially focusing on negative outcomes like casualties and targeting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to civilian populations and concerns about their safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    href
    -0.96
    ologies
    -0.84
    ology
    -0.81
    ologically
    -0.77
    itudinal
    -0.77
    gerald
    -0.76
    Club
    -0.74
    rams
    -0.73
    standing
    -0.72
    gest
    -0.70
    POSITIVE LOGITS
     casualties
    1.01
     casualty
    0.97
     airliner
    0.83
     bystanders
    0.83
     bystand
    0.76
     deaths
    0.74
     zones
    0.72
     evacuation
    0.72
     contractor
    0.72
     contractors
    0.72
    Activations Density 0.036%

    No Known Activations